B
Ben Mildenhall
Researcher at University of California, Berkeley
Publications - 47
Citations - 8171
Ben Mildenhall is an academic researcher from University of California, Berkeley. The author has contributed to research in topics: Rendering (computer graphics) & Computer science. The author has an hindex of 15, co-authored 36 publications receiving 2186 citations. Previous affiliations of Ben Mildenhall include Stanford University & University of California.
Papers
More filters
Posted Content
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
Ben Mildenhall,Pratul P. Srinivasan,Matthew Tancik,Jonathan T. Barron,Ravi Ramamoorthi,Ren Ng +5 more
TL;DR: This work describes how to effectively optimize neural radiance fields to render photorealistic novel views of scenes with complicated geometry and appearance, and demonstrates results that outperform prior work on neural rendering and view synthesis.
Book ChapterDOI
NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
Ben Mildenhall,Pratul P. Srinivasan,Matthew Tancik,Jonathan T. Barron,Ravi Ramamoorthi,Ren Ng +5 more
TL;DR: In this article, a fully-connected (non-convolutional) deep network is used to synthesize novel views of complex scenes by optimizing an underlying continuous volumetric scene function using a sparse set of input views.
Posted Content
Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
Matthew Tancik,Pratul P. Srinivasan,Ben Mildenhall,Sara Fridovich-Keil,Nithin Raghavan,Utkarsh Singhal,Ravi Ramamoorthi,Jonathan T. Barron,Ren Ng +8 more
TL;DR: An approach for selecting problem-specific Fourier features that greatly improves the performance of MLPs for low-dimensional regression tasks relevant to the computer vision and graphics communities is suggested.
Journal ArticleDOI
Local light field fusion: practical view synthesis with prescriptive sampling guidelines
Ben Mildenhall,Pratul P. Srinivasan,Rodrigo Ortiz-Cayon,Nima Khademi Kalantari,Ravi Ramamoorthi,Ren Ng,Abhishek Kar +6 more
TL;DR: An algorithm for view synthesis from an irregular grid of sampled views that first expands each sampled view into a local light field via a multiplane image (MPI) scene representation, then renders novel views by blending adjacent local light fields.
Proceedings ArticleDOI
Burst Denoising with Kernel Prediction Networks
TL;DR: In this paper, a convolutional neural network architecture is proposed for predicting spatially varying kernels that can both align and denoise frames, and a synthetic data generation approach based on a realistic noise formation model, and an optimization guided by an annealed loss function to avoid undesirable local minima.